Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3926 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.6352. Min Act: -0.0001

Data Index: 736696 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.7070. Min Act: -0.0001

Data Index: 958983 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.6391. Min Act: -0.0001

Data Index: 561284 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.5667. Min Act: -0.0001

Data Index: 495951 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.5605. Min Act: -0.0001

Data Index: 1070895 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.5966. Min Act: -0.0001

Data Index: 236392 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.6648. Min Act: -0.0001

Data Index: 615548 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.4493. Min Act: -0.0001

Data Index: 554925 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.3010. Min Act: -0.0001

Data Index: 181267 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.5101. Min Act: -0.0001

Data Index: 503013 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.3190. Min Act: -0.0001

Data Index: 915784 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.4592. Min Act: -0.0001

Data Index: 516083 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.3293. Min Act: -0.0001

Data Index: 358383 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.3335. Min Act: -0.0001

Data Index: 1095027 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.2278. Min Act: -0.0001

Data Index: 40183 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.2874. Min Act: -0.0001

Data Index: 1100607 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.4607. Min Act: -0.0001

Data Index: 1091134 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.1640. Min Act: -0.0001

Data Index: 885249 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.1010. Min Act: -0.0001

Data Index: 642531 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.7070. Min Range: -1.7070

Max Act: 1.3029. Min Act: -0.0001

Data Index: 725278 (C4 (Web Text))

Max Activating Token Index: 131